290 research outputs found
Biologically Inspired Hardware: Status and Perspectives Invited Talk
No full textBiologically Inspired Computing places its emphasis on robustness, adaptability, and emergent organization considering the interaction of many processes. Bio-inspired algorithms exhibit
strength and flexibility in poorly defined or time-variable tasks, as well as when the global behaviour is achieved by simple interacting of species or agents. The above philosophy links various disciplines
such as artificial and computationally intelligence, evolutionary computation, bio-robotics, agent-based systems, and Digital Ecosystems. In this paper, the main branches of bio-inspired computing are briefly discussed. Successively, the impact of the bioinspired
paradigm on innovative hardware structures is outlined
Geometric Calculus Applications to Medical Imaging: Status and Perspectives
No full textMedical imaging data coming from different acquisition modalities requires automatic tools to extract useful information and support clinicians in the formulation of accurate diagnoses. Geometric Calculus (GC) offers a powerful mathematical and computational model for the development of effective medical imaging algorithms. The practical use of GC-based methods in medical imaging requires fast and efficient implementations to meet real-time processing constraints as well as accuracy and robustness requirements. The purpose of this article is to present the state of the art of the GC-based techniques for medical image analysis and processing. The use of GC-based paradigms in Radiomics and Deep Learning, i.e. a comprehensive quantification of tumor phenotypes by applying a large number of quantitative image features and its classification, is also outlined
Design exploration of aes accelerators on FPGAS and GPUs
No full textThe embedded systems are increasingly becoming a key technological component of all kinds of complex tech-nical systems and an exhaustive analysis of the state of the art of all current performance with respect to architectures, design methodologies, test and applications could be very in-teresting. The Advanced Encryption Standard (AES), based on the well-known algorithm Rijndael, is designed to be easily implemented in hardware and software platforms. General purpose computing on graphics processing unit (GPGPU) is an alternative to recongurable accelerators based on FPGA devices. This paper presents a direct comparison between FPGA and GPU used as accelerators for the AES cipher. The results achieved on both platforms and their analysis has been compared to several others in order to establish which device is best at playing the role of hardware accel-erator by each solution showing interesting considerations in terms of throughput, speedup factor, and resource usage. This analysis suggests that, while hardware design on FPGA remains the natural choice for consumer-product design, GPUS are nowadays the preferable choice for PC based ac-celerators, especially when the processing routines are highly parallelizable
Study and Design of Deep Learning Computer-Aided Diagnosis Systems Based on Biomedical Images and Signals
No full textThis Ph.D. thesis aims to describe the research works conducted for the design, the development and the evaluation of innovative Computer-Aided Diagnosis (CAD) systems based on machine learning and deep learning techniques. Several CAD solutions were developed in different medical applications trying to ensure, when possible, three main CAD requirements: improve clinicians performance, reduce or at least not increase clinicians time and integrate the CAD solution in standard procedures. The proposed applications involved images and signals processing; the firsts required the use of different deep learning models to face classification, detection and segmentation problems, while the latter allowed to investigate machine learning as signal processing technique for movement disorder analysis and for a more speculative research in the rehabilitation field. In order to properly validate the proposed algorithms, all the methodologies were applied on real data provided by clinicians, public datasets or specific acquisitions.
Potentialities, challenges and drawbacks about deep learning for medical imaging analysis are discussed in two medical fields, digital pathology and radiology, and complete pipelines are proposed to accomplish three clinical practices: global glomerulosclerosis analysis for Chronic Kidney Disease evaluation, kidneys volume analysis for Autosomal Dominant Polycystic Kidney Disease evaluation and organs segmentation for generic volume quantification. Each study case aims to identify and overcome the limitation of classical image processing techniques, and paves the way towards the clinical use of CAD systems based on deep learning. A second part of this thesis focuses on machine learning and deep learning for signals processing; deep neural networks were investigated for movement disorders analysis and a particular neural model for surface electromyography analysis has been proposed for the evaluation of complex muscle activation patterns, useful in the rehabilitation field. The developed solutions for signals and images processing, were compared with literature standards and, if possible, a personalised classical pipelines has been proposed and customised to face each clinical challenge.
The thesis is divided into six chapters. The first chapter provides an introduction about the reference context. The following chapter two describes the state of the art about traditional CAD systems based on conventional machine learning algorithms, and the novelty that deep learning techniques bring to CADs and medical practices; description of the main convolutional neural network models and autoencoders, and literature about the application of deep learning and machine learning to the concerned medical fields are reported. Chapters three, four and five report the original contribution about the application of deep learning and machine learning techniques to the two types of medical data: images and signals; in detail, chapter three reports the applications in the clinical areas of digital pathology and radiology, focusing on the development of full pipelines based on image analysis; chapter four shows a more speculative research work for signal processing, focusing on the application of undercomplete autoencoders for surface electromyography analysis; chapter five reports the applications of deep neural networks for diseases assessment and grading in subjects affected by movement disorders. The analysed study cases and the contributions reported in this thesis were compared with standard processing techniques ad-hoc developed. Finally, the conclusions about the research works and proposals for future researches are reported in chapter six
An Optimized Architecture for CGA Operations and Its Application to a Simulated Robotic Arm
No full textConformal geometric algebra (CGA) is a new geometric computation tool that is attracting growing attention in many research fields, such as computer graphics, robotics, and computer vision. Regarding the robotic applications, new approaches based on CGA have been proposed to efficiently solve problems as the inverse kinematics and grasping of a robotic arm. The hardware acceleration of CGA operations is required to meet real-time performance requirements in embedded robotic platforms. In this paper, we present a novel embedded coprocessor for accelerating CGA operations in robotic tasks. Two robotic algorithms, namely, inverse kinematics and grasping of a human-arm-like kinematics chain, are used to prove the effectiveness of the proposed approach. The coprocessor natively supports the entire set of CGA operations including both basic operations (products, sums/differences, and unary operations) and complex operations as rigid body motion operations (reflections, rotations, translations, and dilations). The coprocessor prototype is implemented on the Xilinx ML510 development platform as a complete system-on-chip (SoC), integrating both a PowerPC processing core and a CGA coprocessing core on the same Xilinx Virtex-5 FPGA chip. Experimental results show speedups of 78x and 246x for inverse kinematics and grasping algorithms, respectively, with respect to the execution on the PowerPC processor
A Novel Approach for Faulty Sensor Detection and Data Correction in Wireless Sensor Network
No full texthe main Wireless Sensor Networks purpose is represented by areas of interest monitoring. Even if the Wireless sensor network is properly initialized, errors can occur during its monitoring tasks. The present work describes an approach for detecting faulty sensors in Wireless Sensor Network and for correcting their corrupted data. The approach is based on the assumption that exist a spatio-temporal cross- correlations among sensors. Two sequential mathematical tools are used. The first stage is a probabilistic tools, namely Markov Random Field, for a two-fold sensor classification (working or damaged). The last stage is represented by the Locally Weighted Regression model, a learning techniques modelling each sensor on the basis of its neighbours. If the sensor is working, the approach actives a learning phase and the sensor model is trained, while if the sensor is damaged, a correction phase starts and the related corrupted data are replaced with the data produced by the learned model. The effectiveness of the proposed approach has been proved using real data obtained from the Intel Berkeley Research Laboratory, over which different classes of faults were artificially superimposed. The proposed architecture achieves satisfactory results, since it successfully corrects faulty data produced by sensors
- …
